II.
EvalRun overview
Reference · liveeval-run:gpqa-diamond.claude-opus-4-5.2025-09
eval-run:gpqa-diamond.claude-opus-4-5.2025-09 overview
Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for eval-run:gpqa-diamond.claude-opus-4-5.2025-09.
Attributes
target
benchmarkId
testSetId
targetId
runAt
2025-09-29T00:00:00Z
runBy
anthropic
configHash
Outgoing edges
evaluates_target1
- model:claude-opus-4-5@current·ModelVersionClaude 4.5 Opus
for_benchmark1
- benchmark:gpqa·BenchmarkGPQA
uses_test_set1
- test-set:gpqa-diamond-2024·TestSetGPQA Diamond — 2024 release
Incoming edges
belongs_to_eval_run1
- eval-result:gpqa-diamond.claude-opus-4-5.001·EvalResult